Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Search on GAIA text-only (val)

70.9Accuracy

Tongyi-DeepResearch

36.5845.4954.463.31Jan 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
70.9
2026.01
70.5
2026.01
66
2026.01
63.1
2026.01
56.3
2026.01
55.3
2026.01
53.7
2026.01
52.8
2026.01
52.8
2026.01
51.5
2026.01
51.1
2026.01
51.1
2026.01
50.8
2026.01
50.2
2026.01
50
2026.01
48.9
2026.01
46
2026.01
46
2026.01
42.4
2026.01
42.4
2026.01
41.1
2026.01
40.5
2026.01
39.5
2026.01
37.9